mlsanityData to 14 Oct 2026

PatFig: Generating Short and Long Captions for Patent Figures

arXiv 2309.08379 ↗First posted 15 Sep 2023cs.CV cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper introduces Qatent PatFig, a novel large-scale patent figure dataset comprising 30,000+ patent figures from over 11,000 European patent applications. For each figure, this dataset provides short and long captions, reference numerals, their corresponding terms, and the minimal claim set that describes the interactions between the components of the image. To assess the usability of the dataset, we finetune an LVLM model on Qatent PatFig to generate short and long descriptions, and we investigate the effects of incorporating various text-based cues at the prediction stage of the patent figure captioning process.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 15 Sep 2023.

Builds on

16 of 41 references.

References · 16

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  4. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  5. 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,046
  6. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  7. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,423
  8. 2021Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Conceptscited by 1,216
  9. 2018DVQA: Understanding Data Visualizations via Question Answeringcited by 340
  10. 2017FigureQA: An Annotated Figure Dataset for Visual Reasoningcited by 319
  11. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  12. 2021SciCap: Generating Captions for Scientific Figurescited by 77
4 more
  1. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  2. 2019Figure Captioning with Reasoning and Sequence-Level Trainingcited by 21
  3. 2023DocTr: Document Transformer for Structured Information Extraction in Documentscited by 18
  4. 2022Abstract Images Have Different Levels of Retrievability Per Reverse Image Search Enginecited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 6; 2025: 5.

12 papers.

  1. 2023GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captionscited by 21
  2. 2024Natural Language Processing in the Patent Domain: A Surveycited by 20
  3. 2024Can Large Language Models Generate High-quality Patent Claims?cited by 19
  4. 2025PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figurescited by 7
  5. 2024Patent-CR: A Dataset for Patent Claim Revisioncited by 4
  6. 2024DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Modelscited by 3
  7. 2025AutoSpec: An Agentic Framework for Automatically Drafting Patent Specificationcited by 3
  8. 2024Exploiting LMM-based knowledge for image classification taskscited by 2
  9. 2024SkinGEN: an Explainable Dermatology Diagnosis-to-Generation Framework with Interactive Vision-Language Modelscited by 1
  10. 2025PatentVision: A multimodal method for drafting patent applicationscited by 1
  11. 2025Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrievalcited by 0
  12. 2025Patentformer: A demonstration of AI-assisted automated patent draftingcited by 0